How to Use the Ghost MCP in Google ADK

Q: How do I configure Ghost with Google ADK?

Run pip install google-adk in your terminal. Set up the connection using McpToolset(serverparams=StreamableHttpServerParameters(url="...")). Pass that toolset to your LlmAgent constructor.

Q: Can I restrict which Ghost MCP tools Google ADK accesses?

You control this entirely. Use the toolnames parameter when initializing the toolset. This prevents the agent from calling endpoints like createpost if you only want read access.

Q: How do the Ghost MCP Server and Google ADK handle newsletters?

The server provides a listnewsletters endpoint. Your agent reads the current newsletter configurations to understand your distribution channels. It does not trigger the actual email sends.

Q: What details does the post retrieval tool provide?

Calling getpostdetails returns the full HTML or text content of an article. It requires a specific post ID. You typically run listposts first to get those IDs.

Feed your Ghost publication data directly into Google ADK to analyze members and automate drafts with Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ghost MCP to Google ADK

Create your Vinkius account to connect Ghost to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Ghost with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Mass Content Audits with Gemini

The `list_posts` tool extracts the metadata and IDs for your entire Ghost blog archive. Your agent feeds this list into Gemini's massive 1M+ token context window. This allows the model to analyze your entire publication history at once. For deeper analysis, the agent calls `get_post_details` on specific IDs to read the full text. You can pipe this output directly into BigQuery for long-term storage or trend analysis. The Google ADK makes moving this text between your CMS and Google Cloud trivial.

Ghost MCP Server Audience Analytics

Pulling your subscriber list requires a single call to the `list_members` tool. Your agent receives emails, join dates, and subscription statuses. It drops this raw data into Vertex AI to predict churn rates or identify your most loyal readers. You then use `list_membership_tiers` to understand the paid structure of your site. If you want to run a promotion, the agent checks `list_offers` to see what discounts exist. This connects your revenue data directly to your enterprise analytics pipeline.

Programmatic Publishing Pipeline

Generating new content starts with the `create_post` tool. You provide a title and HTML content, and the server creates a draft by default. Your agent can also push it live immediately if you bypass the draft stage. Before writing, the agent checks `list_tags` to ensure it applies the correct categorization. It also verifies your static routing with `list_pages` and confirms the site identity via `get_site_settings`. You restrict which of these tools the model can access using the `tool_names` filter in your setup.

Setup guide

Set up Ghost MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Ghost tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Ghost_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Ghost tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Ghost. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Ghost now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Ghost MCP in Google ADK

Run `pip install google-adk` in your terminal. Set up the connection using `McpToolset(server_params=StreamableHttpServerParameters(url="..."))`. Pass that toolset to your `LlmAgent` constructor.

You control this entirely. Use the `tool_names` parameter when initializing the toolset. This prevents the agent from calling endpoints like `create_post` if you only want read access.

The server provides a `list_newsletters` endpoint. Your agent reads the current newsletter configurations to understand your distribution channels. It does not trigger the actual email sends.

Calling `get_post_details` returns the full HTML or text content of an article. It requires a specific post ID. You typically run `list_posts` first to get those IDs.

The integration touches sensitive subscriber emails and payment statuses through `list_members` and `list_membership_tiers`. Vinkius handles the authentication using a single zero-trust endpoint token. The ephemeral nature of the sandbox means no data lingers after the request completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript